Papers › TorchBeast: A PyTorch Platform for Distributed RL

TorchBeast: A PyTorch Platform for Distributed RL

8 Oct 2019arXiv:1910.03552archive 2025-07-28

Heinrich Küttler, Nantas Nardelli, Thibaut Lavril, Marco Selvatici, Viswanath Sivakumar, Tim Rocktäschel, Edward Grefenstette

TorchBeast is a platform for reinforcement learning (RL) research in PyTorch. It implements a version of the popular IMPALA algorithm for fast, asynchronous, parallel training of RL agents. Additionally, TorchBeast has simplicity as an explicit design goal: We provide both a pure-Python implementation ("MonoBeast") as well as a multi-machine high-performance version ("PolyBeast"). In the latter, parts of the implementation are written in C++, but all parts pertaining to machine learning are kept in simple Python using PyTorch, with the environments provided using the OpenAI Gym interface. This enables researchers to conduct scalable RL research using TorchBeast without any programming knowledge beyond Python and PyTorch. In this paper, we describe the TorchBeast design principles and implementation and demonstrate that it performs on-par with IMPALA on Atari. TorchBeast is released as an open-source package under the Apache 2.0 license and is available at \url{https://github.com/facebookresearch/torchbeast}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1910.03552")

Code

Syntology Ran 4 of 9 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 6 samples from 1 repository, 1 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

heiner/scalable_agent officialmentioned in papertfApache-2.0 report
facebookresearch/mvfst-rl mentioned on GitHubpytorchNOASSERTION report
facebookresearch/torchbeast mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 4 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
1ran · fixture could not drive it
5unverified

Licence: 3 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from heiner/scalable_agent. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

log_probs_from_logits_and_actions heiner/scalable_agent/vtrace.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · a75de4dc4c61d7dc · report
compute_baseline_loss heiner/scalable_agent/experiment.py official repository unverified Apache-2.0 (permissive) · 777b5a676e76d593 · report
compute_entropy_loss heiner/scalable_agent/experiment.py official repository unverified Apache-2.0 (permissive) · 50c20c55f1b07c8e · report
compute_human_normalized_score heiner/scalable_agent/dmlab30.py official repository unverified Apache-2.0 (permissive) · be48a80c545e0430 · report
from_importance_weights heiner/scalable_agent/vtrace.py official repository unverified Apache-2.0 (permissive) · e11ee068514828e6 · report
from_logits heiner/scalable_agent/vtrace.py official repository unverified Apache-2.0 (permissive) · 1175c77e601077b8 · report
compute_baseline_loss identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · e9123707cba84b2c · report
compute_entropy_loss identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · a27a9dc97eefda7f · report
compute_policy_gradient_loss identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · d6d7e0906f1c57b2 · report

Tasks

OpenAI GymReinforcement LearningReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: TorchBeast

ConvolutionEntropy RegularizationExperience ReplayGradient ClippingIMPALALSTMMax PoolingRMSPropReLUResidual ConnectionSigmoid ActivationTanh ActivationTorchBeastV-trace

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections